Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/87524
Title: Temperature based restricted boltzmann machines
Authors: Li, Guoqi
Deng, Lei
Xu, Yi
Wen, Changyun
Wang, Wei
Pei, Jing
Shi, Luping
Keywords: Restricted Boltzmann Machines
DRNTU::Engineering::Electrical and electronic engineering
Temperature
Issue Date: 2016
Source: Li, G., Deng, L., Xu, Y., Wen, C., Wang, W., Pei, J., & Shi, L. (2016). Temperature based restricted boltzmann machines. Scientific Reports, 6, 19133-. doi:10.1038/srep19133
Series/Report no.: Scientific Reports
Abstract: Restricted Boltzmann machines (RBMs), which apply graphical models to learning probability distribution over a set of inputs, have attracted much attention recently since being proposed as building blocks of multi-layer learning systems called deep belief networks (DBNs). Note that temperature is a key factor of the Boltzmann distribution that RBMs originate from. However, none of existing schemes have considered the impact of temperature in the graphical model of DBNs. In this work, we propose temperature based restricted Boltzmann machines (TRBMs) which reveals that temperature is an essential parameter controlling the selectivity of the firing neurons in the hidden layers. We theoretically prove that the effect of temperature can be adjusted by setting the parameter of the sharpness of the logistic function in the proposed TRBMs. The performance of RBMs can be improved by adjusting the temperature parameter of TRBMs. This work provides a comprehensive insights into the deep belief networks and deep learning architectures from a physical point of view.
URI: https://hdl.handle.net/10356/87524
http://hdl.handle.net/10220/46750
DOI: http://dx.doi.org/10.1038/srep19133
Rights: © 2016 The Authors (Nature Publishing Group). This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
Temperature based Restricted Boltzmann Machines.pdf1.37 MBAdobe PDFThumbnail
View/Open

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.